Training in progress, step 38000, checkpoint

last-checkpoint/README.md

@@ -1273,6 +1273,10 @@ You can finetune this model on your own dataset.
 | 0.6662 | 37700 | 0.3           |
 | 0.6671 | 37750 | 0.3147        |
 | 0.6680 | 37800 | 0.2895        |
+| 0.6688 | 37850 | 0.2649        |
+| 0.6697 | 37900 | 0.287         |
+| 0.6706 | 37950 | 0.267         |
+| 0.6715 | 38000 | 0.2862        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2bc434db7c929c75024a831ecc5cc03d8b7a4eddd4dd3db1978cf30bffea991
+oid sha256:f0d08023f1bb62ce1d0130d07526322a2c5fda70606088482affec032e342b5c
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0610d398ebf6d38b0b9cbf0894fccceee41b5214e963879ca6b28162561c192a
+oid sha256:d8b44bc19e6a23e08867d09cb20779d3a37e861123bffe86f50954d881ed4c90
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d58558a83c013260c9bf646c050a79e224f490d790bbdf4116e8fa1e264f106
+oid sha256:28b8300b2a2312e0bd0c6c541da810ac2f229a1e589baac1c616b441c52c2040
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:381cb302a73675bf2179ed8dcab807616061c0bb5718d119ea0e96650e118eb1
+oid sha256:0c9e92d7ca7e11f8c8280a110c0e95f7fc8368104e07cf4940880e3ea39426da
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a32f613d93659adf5731cade217c9a9122ff518b0d84ca3c2508b48b15899d8
+oid sha256:604774c1c43f2a9fc2aaee736abd7cd490fcb173a1997d86fd932e858e22ca53
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.667950734215688,
+  "epoch": 0.6714848650845541,
   "eval_steps": 500,
-  "global_step": 37800,
+  "global_step": 38000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5300,6 +5300,34 @@
       "learning_rate": 1.846125149712356e-05,
       "loss": 0.2895,
       "step": 37800
+    },
+    {
+      "epoch": 0.6688342669329045,
+      "grad_norm": 1.7297286987304688,
+      "learning_rate": 1.8412165478785025e-05,
+      "loss": 0.2649,
+      "step": 37850
+    },
+    {
+      "epoch": 0.669717799650121,
+      "grad_norm": 1.2361524105072021,
+      "learning_rate": 1.8363079460446486e-05,
+      "loss": 0.287,
+      "step": 37900
+    },
+    {
+      "epoch": 0.6706013323673375,
+      "grad_norm": 1.472721815109253,
+      "learning_rate": 1.831399344210795e-05,
+      "loss": 0.267,
+      "step": 37950
+    },
+    {
+      "epoch": 0.6714848650845541,
+      "grad_norm": 1.7498071193695068,
+      "learning_rate": 1.8264907423769416e-05,
+      "loss": 0.2862,
+      "step": 38000
     }
   ],
   "logging_steps": 50,